Symposium on Interdisciplinary Research for Fashion & Textile

Programme Rundown (Click HERE for details)

Keynote Speakers (in order of appearance):

Prof. Xungai Wang

Associate Dean (Strategic Planning and Development) & Chair Professor of Fiber Science and Technology, School of Fashion and Textiles

View Speaker's Website

Title

New Uses for Old Textiles

Abstract

The growing volume of textile waste has become a major global concern. This presentation will cover our recent research work on exploring new uses for waste textiles. A unique aspect of the work is in utilizing the color of waste textiles. Colored textile waste, such as denim, was turned into pigment like powders, and the colored powders were then coated or printed onto white fabrics to achieve new color effects. When fibers such as wool were converted into fine powder, the powder could be dyed with conventional dyes even at room temperature. Some waste textiles could also be regenerated into new fibers, either with or without color. Other uses of waste textiles will also be briefly discussed in the presentation.

Dr Sylvia Liu

Associate Director, RCTFF & Assistant Dean (Academic Programmes), School of Design

View Speaker's Website

Title

Fashion Entrepreneurship in a VUCA World

Abstract

How to manage design business effectively and efficiently is always a challenge to design business owners and key stakeholders in the innovation ecosystem. In a conventional business context, capability models of managing design in projects, teams and firms were developed to evaluate their maturity and guide their practice. However, in today’s VUCA world, which stands for volatility, uncertainty, complexity and ambiguity, the capabilities of managing a design business are unknown. This is the research topic of Dr. Liu’s team. She will introduce the new model developed by her and the evaluation results of Hong Kong fashion design start-ups. 

Dr Dahua Shou

Limin Endowed Young Scholar in Advanced Textiles Technologies & Associate Professor, School of Fashion and Textiles

View Speaker's Website

Title

Personalizing Moisture and Thermal Management

Abstract

As global temperatures reach unprecedented highs in 2024, the development of innovative moisture and thermal management materials becomes increasingly crucial. With the fast-approaching 2024 Paris Olympics, there is a pressing need for advanced textiles and wearable technologies to regulate heat and moisture effectively. This speech will introduce the latest breakthroughs in personalizing thermal and moisture management technologies, showcasing innovations such as Sweatextile, Omni-Cool-Dry, iActive, and Soft Robotic Clothing.

These cutting-edge advancements represent a significant leap in designing textiles that adapt to the body’s evolving requirements for comfort, performance, and well-being. Sweatextile replicates the skin’s natural sweating process to facilitate rapid and directional moisture transfer, ensuring dryness and breathability. Omni-Cool-Dry, inspired by beetles, offers exceptional cooling by both reflecting solar radiation and emitting body heat. iActive incorporates artificial sweat glands and an intricate root-like liquid transport system for superior perspiration control and dissipation. Soft Robotic Clothing employs embedded skeleton-like flexible actuators to adjust to temperature variations, providing optimal thermoregulation.

Dr Yancheng Yuan

Assistant Professor, Department of Data Science and Artificial Intelligence

View Speaker's Website

Title

DreamRec: Reshape the Sequential Recommendation Systems

Abstract

Sequential recommendation aims to recommend the next item that matches a user’s interest, based on the sequence of items he/she interacted with before. Scrutinizing previous studies, we can summarize a common learning-to-classify paradigm — given a positive item, a recommender model performs negative sampling to add negative items and learns to classify whether the user prefers them or not, based on his/her historical interaction sequence. Although effective, we reveal two inherent limitations: (1) it may differ from human behavior in that a user could imagine an oracle item in mind and select potential items matching the oracle; and (2) the classification is limited in the candidate pool with noisy or easy supervision from negative samples, which dilutes the preference signals towards the oracle item. Yet, generating the oracle item from the historical interaction sequence is mostly unexplored. To bridge the gap, we reshape sequential recommendation as a learning-to-generate paradigm, which is achieved via a guided diffusion model, termed DreamRec. To better understand the generated  oracle items, we leverage the power of Large Language Models by designing a novel residual prompting learning mechanism. Numerical results on large recommendation datasets demonstrate the superior performance of our proposed generative sequential recommendation paradigm.

Dr Ping Li

Assistant Professor, Department of Computing

View Speaker's Website

Title

Exploration of Visual Art, Fashion and Design Synthesis

Abstract

Art, fashion and design synthesis as an expressive way for producing user-desired appearances has received much attention in creative media research. In interactive design, it would be very powerful to render the specially stylized presentation of interested objects virtually using artificial-intelligence-aided design tools for artistic effects rendering and synthesis. However, existing special effects and artistic synthesis methods focus directly on artistic modelling in the fields of color space and rarely consider the artistic nature and rich detailed structure design of the input visual media, which unavoidably leads to the loss of key information for understanding. In this talk, we will consider perceptual computational art and media synthesis, focusing on the efficient generation, perception, rendering of visual art, fashion and design, and their exploration in creative media. In the future, we will further extend the artistic rending and synthesis to more complicated 2D/3D video applications with large motion and occluded scene. We will also work on special design effects synthesis by the inspiration of latest real-time 2D/3D vision and graphics learning techniques.